B bÿ@sdZddlmZmZmZGdddeZGdddeZGdddeZGd d d eZGd d d eZ Gd ddeZ GdddeZ GdddeZ GdddeZ GdddeZGdddeZGdddeZGdddeZGdddeZGdd d eZGd!d"d"eZGd#d$d$eZGd%d&d&eZGd'd(d(eZGd)d*d*eZGd+d,d,eZGd-d.d.eZGd/d0d0eZGd1d2d2eZGd3d4d4eZGd5d6d6eZGd7d8d8eZe d9krdd:l!m"Z"e"d;S)>> cline = Primer3Commandline(sequence="mysequence.fas", auto=True, hybridprobe=True) >>> cline.explainflag = True >>> cline.osizeopt=20 >>> cline.psizeopt=200 >>> cline.outfile = "myresults.out" >>> cline.bogusparameter = 1967 # Invalid parameter Traceback (most recent call last): ... ValueError: Option name bogusparameter was not found. >>> print(cline) eprimer3 -auto -outfile=myresults.out -sequence=mysequence.fas -hybridprobe=True -psizeopt=200 -osizeopt=20 -explainflag=True eprimer3c4Ksvtddgdddtddgdtd d gd td d gdtddgdtddgdtddgdtddgdtddgdtddgd td!d"gd#td$d%gd&td'd(gd)td*d+gd,td-d.gd/td0d1gd2td3d4gd5td6d7gd8td9d:gd;tdtd?d@gdAtdBdCgdDtdEdFgdGtdHdIgdJtdKdLgdMtdNdOgdPtdQdRgdStdTdUgdVtdWdXgdYtdZd[gd\td]d^gd_td`dagdbtdcddgdetdfdggdhtdidjgdktdldmgdntdodpgdqtdrdsgdttdudvgdwtdxdygdztd{d|gd}td~dgdtddgdtddgdtddgdtddgdtddgdtddgdtddgdtddgdg2|_tj||f|dS)zInitialize the class.z -sequencesequencez Sequence to choose primers from.T) is_requiredz-taskZtaskz#Tell eprimer3 what task to perform.z -hybridprobeZ hybridprobez-Find an internal oligo to use as a hyb probe.z -numreturnZ numreturnz)Maximum number of primer pairs to return.z-includedregionZincludedregionz3Subregion of the sequence in which to pick primers.z-targettargetz(Sequence to target for flanking primers.z-excludedregionZexcludedregionz'Regions to exclude from primer picking.z -forwardinputZ forwardinputz&Sequence of a forward primer to check.z -reverseinputZ reverseinputz&Sequence of a reverse primer to check.z-gcclampZgcclampz:The required number of Gs and Cs at the 3' of each primer.z-osizeZosizez!Optimum length of a primer oligo.z-minsizeZminsizez!Minimum length of a primer oligo.z-maxsizemaxsizez!Maximum length of a primer oligo.z-otmZotmz[Melting temperature for primer oligo (OBSOLETE). Option replaced in EMBOSS 6.6.0 by -opttmz-opttmZopttmz]Optimum melting temperature for a primer oligo. Option added in EMBOSS 6.6.0, replacing -otmz-mintmZmintmz/Minimum melting temperature for a primer oligo.z-maxtmZmaxtmz/Maximum melting temperature for a primer oligo.z -maxdifftmZ maxdifftmzOMaximum difference in melting temperatures between forward and reverse primers.z -ogcpercentZ ogcpercentzOptimum GC% for a primer.z-mingcZmingczMinimum GC% for a primer.z-maxgcZmaxgczMaximum GC% for a primer.z -saltconcZsaltconcz)Millimolar salt concentration in the PCR.z-dnaconcZdnaconcz7Nanomolar concentration of annealing oligos in the PCR.z -maxpolyxZmaxpolyxz;Maximum allowable mononucleotide repeat length in a primer.z -psizeoptZpsizeoptz!Optimum size for the PCR product.z-prangeZprangez/Acceptable range of length for the PCR product.z-ptmoptZptmoptz0Optimum melting temperature for the PCR product.z-ptmminZptmminz5Minimum allowed melting temperature for the amplicon.z-ptmmaxZptmmaxz5Maximum allowed melting temperature for the amplicon.z-oexcludedregionZoexcludedregionz+Do not pick internal oligos in this region.z -oligoinputZ oligoinputzSequence of the internal oligo.z -osizeoptZosizeoptz!Optimum length of internal oligo.z -ominsizeZominsizez!Minimum length of internal oligo.z -omaxsizeZomaxsizez!Maximum length of internal oligo.z-otmoptZotmoptz.Optimum melting temperature of internal oligo.z-otmminZotmminz.Minimum melting temperature of internal oligo.z-otmmaxZotmmaxz.Maximum melting temperature of internal oligo.z-ogcoptZogcoptzOptimum GC% for internal oligo.z-ogcminZogcminzMinimum GC% for internal oligo.z-ogcmaxZogcmaxzMaximum GC% for internal oligo.z -osaltconcZ osaltconcz6Millimolar concentration of salt in the hybridisation.z -odnaconcZodnaconcz?Nanomolar concentration of internal oligo in the hybridisation.z -oanyselfZoanyselfz;Maximum allowable alignment score for self-complementarity.z -oendselfZoendselfz 0.001)z -invarfracZ invarfraczproportoin of invariant sitesz-ttratiottratioz ts/tv ratioz -freqsfromZ freqsfromzuse emprical base freqsz -basefreqbasefreqzspecify basefreqsz-lowerlowerzlower triangle matrix (y/N)N)rrrr)rrrrrrr_s*          zFDNADistCommandline.__init__N)r,)rrrrrrrrrr+Xsr+c@seZdZdZdddZdS)FTreeDistCommandlinezCommandline object for the ftreedist program from EMBOSS. ftreedist is an EMBOSS wrapper for the PHYLIP program treedist used for calulating distance measures between phylogentic trees. ftreedistcKshtddgddddtddgdtd d gd td d gdtddgdtddgdg|_tj||f|dS)zInitialize the class.z -intreefile intreefileztree file to score (phylip)T)rr#z-dtypeZdtypez*distance type ([S]ymetric, [b]ranch score)z-pairingZpairingzzWrite trees to file (Y/n)z -outtreefiler?zfilename for output treez-dotdiffrCzUse dot-differencing? [Y/n]N)rrrr)rrrrrrrs.            zFDNAParsCommandline.__init__N)rE)rrrrrrrrrrDsrDc@seZdZdZdddZdS)FProtParsCommandlineaCommandline object for the fdnapars program from EMBOSS. fprotpars is an EMBOSS version of the PHYLIP program protpars, for estimating trees from protein sequences using parsiomny. Calling this command without providing a value for the option "-intreefile" will invoke "interactive mode" (and as a result fail if called with subprocess) if "-auto" is not set to true. fprotparscKstddgddddtddgdtd d gd dddtd d gdtddgdtddgdtddgdtddgdtddgdtddgd td!d"gd#td$d%gd&g |_tj||f|d'S)(zInitialize the class.z -sequencer"zseq file to use (phylip)T)rr#z -intreefiler8zPhylip tree file to scorez -outtreefiler?zphylip tree output filez-weightsr1z weights filez -whichcode whichcodez which genetic code, [U,M,V,F,Y]]z-njumblerFz7number of times to randomise input order (default is 0)z-seedr=zprovide random seedz-outgrnor9zSpecify outgroupz-threshrGzUse threshold parsimony (y/N)z -thresholdrHzThreshold valuez-troutr>zWrite trees to file (Y/n)z-dotdiffrCzUse dot-differencing? [Y/n]N)rrrr)rrrrrrrs.        zFProtParsCommandline.__init__N)rJ)rrrrrrrrrrI srIc@seZdZdZdddZdS)FProtDistCommandlinezCommandline object for the fprotdist program from EMBOSS. fprotdist is an EMBOSS wrapper for the PHYLIP program protdist used to estimate trees from protein sequences using parsimony fprotdistcKstddgddddtddgdtd d gd td d gdtddgdtddgdtddgdtddgdtddgdtddgd td!d"gd#td$d%gd&td'd(gd)td*d+gd,g|_tj||f|d-S).zInitialize the class.z -sequencer"zseq file to use (phylip)T)rr#z -ncategoriesr/z number of rate catergories (1-9)z-rater0zrate for each categoryz -catergoriesrBz file of ratesz-weightsr1z weights filez-methodr-zsub. model [j,h,d,k,s,c]z-gammar.zgamma [g, i,c]z-gammacoefficientr2zvalue for gamma (> 0.001)z-invarcoefficientZinvarcoefficientz4float for variation of substitution rate among sitesz-aacategZaacategz"Choose the category to use [G,C,H]z -whichcoderKzgenetic code [c,m,v,f,y]z-easeZeasez-Pob change catergory (float between -0 and 1)z-ttratior3z#Transition/transversion ratio (0-1)z -basefreqr4z+DNA base frequencies (space separated list)N)rrrr)rrrrrrr>s0           zFProtDistCommandline.__init__N)rM)rrrrrrrrrrL7srLc@seZdZdZdddZdS)FConsenseCommandlinezCommandline object for the fconsense program from EMBOSS. fconsense is an EMBOSS wrapper for the PHYLIP program consense used to calculate consensus trees. fconsensec Ksttddgddddtddgdtd d gd td d gdtddgdtddgdtddgdg|_tj||f|dS)zInitialize the class.z -intreefiler8z-file with phylip trees to make consensus fromT)rr#z-methodr-z!consensus method [s, mr, MRE, ml]z-mlfracZmlfracz8cut-off freq for branch to appear in consensus (0.5-1.0)z-rootrootztreat trees as rooted (YES, no)z-outgrnor9z&OTU to use as outgroup (starts from 0)z-troutr>z -outtreefiler?z"Phylip tree output file (optional)N)rrrr)rrrrrrrhs    zFConsenseCommandline.__init__N)rO)rrrrrrrrrrNasrNc@seZdZdZdddZdS)WaterCommandlinez5Commandline object for the water program from EMBOSS.waterc Kstddgddddtddgddddtd d gd dd td dgddd tddgdddtddgdtddgdtddgdtddgdtd d!gd"td#d$gd%g |_tj||f|d&S)'zInitialize the class.z -asequence asequencezFirst sequence to alignT)rr#z -bsequence bsequencezSecond sequence to alignz-gapopengapopenzGap open penalty)r#z -gapextend gapextendzGap extension penaltyz -datafiler<z Matrix file)rz-nobriefnobriefz(Display extended identity and similarityz-briefbriefz%Display brief identity and similarityz -similarity similarityz'Display percent identity and similarityz -snucleotider)z"Sequences are nucleotide (boolean)z -sproteinr*zSequences are protein (boolean)z-aformataformatz5Display output in a different specified output formatN)rrrrr)rrrrrrrs4      zWaterCommandline.__init__N)rR)rrrrrrrrrrQsrQc@seZdZdZdddZdS)NeedleCommandlinez6Commandline object for the needle program from EMBOSS.needlecKstddgddddtddgddddtd d gd dd td dgddd tddgdddtddgdtddgdtddgdtddgdtd d!gd"td#d$gd%td&d'gd(td)d*gd+td,d-gd.g|_tj||f|d/S)0zInitialize the class.z -asequencerSzFirst sequence to alignT)rr#z -bsequencerTzSecond sequence to alignz-gapopenrUzGap open penalty)r#z -gapextendrVzGap extension penaltyz -datafiler<z Matrix file)rz -endweight endweightzApply And gap penaltiesz-endopenendopenz0The score taken away when an end gap is created.z -endextend endextendzPThe score added to the end gap penality for each base or residue in the end gap.z-nobriefrWz(Display extended identity and similarityz-briefrXz%Display brief identity and similarityz -similarityrYz'Display percent identity and similarityz -snucleotider)z"Sequences are nucleotide (boolean)z -sproteinr*zSequences are protein (boolean)z-aformatrZz5Display output in a different specified output formatN)rrrrr)rrrrrrrsB       zNeedleCommandline.__init__N)r\)rrrrrrrrrr[sr[c@seZdZdZdddZdS)NeedleallCommandlinez9Commandline object for the needleall program from EMBOSS. needleallcKstddgddddtddgddddtd d gd dd td dgddd tddgdddtddgdtddgdtddgdtddgdtd d!gd"td#d$gd%td&d'gd(td)d*gd+td,d-gd.td/d0gd1td2d3gd4g|_tj||f|d5S)6zInitialize the class.z -asequencerSzFirst sequence to alignT)rr#z -bsequencerTzSecond sequence to alignz-gapopenrUzGap open penalty)r#z -gapextendrVzGap extension penaltyz -datafiler<z Matrix file)rz -minscoreminscorez:Exclude alignments with scores below this threshold score.z -errorfileZ errorfilezError file to be written to.z -endweightr]zApply And gap penaltiesz-endopenr^z0The score taken away when an end gap is created.z -endextendr_zPThe score added to the end gap penality for each base or residue in the end gap.z-nobriefrWz(Display extended identity and similarityz-briefrXz%Display brief identity and similarityz -similarityrYz'Display percent identity and similarityz -snucleotider)z"Sequences are nucleotide (boolean)z -sproteinr*zSequences are protein (boolean)z-aformatrZz5Display output in a different specified output formatN)rrrrr)rrrrrrrsJ        zNeedleallCommandline.__init__N)ra)rrrrrrrrrr`sr`c@seZdZdZdddZdS)StretcherCommandlinez9Commandline object for the stretcher program from EMBOSS. stretcherc Kstddgddddtddgddddtd d gd dd d dtddgdddd dtddgdddtddgdtddgdtddgdg|_tj||f|d S)!zInitialize the class.z -asequencerSzFirst sequence to alignT)rr#z -bsequencerTzSecond sequence to alignz-gapopenrUzGap open penaltycSs t|tS)N) isinstanceint)valuerrr-z/StretcherCommandline.__init__..)r#Zchecker_functionz -gapextendrVzGap extension penaltycSs t|tS)N)rerf)rgrrrrh3riz -datafiler<z Matrix file)rz -snucleotider)z"Sequences are nucleotide (boolean)z -sproteinr*zSequences are protein (boolean)z-aformatrZz5Display output in a different specified output formatN)rrrr)rrrrrrrs8     zStretcherCommandline.__init__N)rd)rrrrrrrrrrcsrcc@seZdZdZdddZdS)FuzznucCommandlinez7Commandline object for the fuzznuc program from EMBOSS.fuzznuccKs^tddgdddtddgdddtd d gd td d gdtddgdg|_tj||f|dS)zInitialize the class.z -sequencer"zSequence database USAT)r#z-patternpatternz5Search pattern, using standard IUPAC one-letter codesz -pmismatch pmismatchzNumber of mismatchesz -complementZ complementzSearch complementary strandz-rformatrformatz'Specify the report format to output in.N)rrrr)rrrrrrrEs  zFuzznucCommandline.__init__N)rk)rrrrrrrrrrjBsrjc@seZdZdZdddZdS)FuzzproCommandlinez7Commandline object for the fuzzpro program from EMBOSS.fuzzprocKsRtddgdddtddgdddtd d gd td d gdg|_tj||f|dS)zInitialize the class.z -sequencer"zSequence database USAT)r#z-patternrlz5Search pattern, using standard IUPAC one-letter codesz -pmismatchrmzNumber of mismatchesz-rformatrnz'Specify the report format to output in.N)rrrr)rrrrrrrZs zFuzzproCommandline.__init__N)rp)rrrrrrrrrroWsroc@seZdZdZdddZdS)Est2GenomeCommandlinez:Commandline object for the est2genome program from EMBOSS. est2genomecKstddgdddtddgdddtd d gd td d gdtddgdtddgdtddgdtddgdtddgdtddgd td!d"gd#td$d%gd&td'd(gd)td*d+gd,td-d.gd/td0d1gd2td3d4gd5g|_tj||f|d6S)7zInitialize the class.z-estZestzEST sequence(s)T)r#z-genomeZgenomezGenomic sequencez-matchmatchzScore for matching two basesz -mismatchmismatchzCost for mismatching two basesz -gappenaltyZ gappenaltyzECost for deleting a single base in either sequence, excluding intronsz-intronpenaltyZ intronpenaltyz*Cost for an intron, independent of length.z-splicepenaltyZ splicepenaltyzUCost for an intron, independent of length and starting/ending on donor-acceptor sitesz -minscorerbz:Exclude alignments with scores below this threshold score.z-reversereversez+Reverse the orientation of the EST sequencez-spliceZsplicez$Use donor and acceptor splice sites.z-modemodezCThis determines the comparion mode. 'both', 'forward', or 'reverse'z-bestZbestz:You can print out all comparisons instead of just the bestz-spaceZspacezfor linear-space recursion.z-shuffleZshuffleZShufflez-seedr=zRandom number seedz-alignZalignzShow the alignment.z-widthwidthzAlignment widthN)rrrr)rrrrrrrns>        zEst2GenomeCommandline.__init__N)rr)rrrrrrrrrrqksrqc@seZdZdZdddZdS)ETandemCommandlinez7Commandline object for the etandem program from EMBOSS.etandemc Ks|tddgddddtddgddd td d gd dd td dgdtddgdtddgdtddgdg|_tj||f|dS)zInitialize the class.z -sequencer"SequenceT)rr#z -minrepeatZ minrepeatzMinimum repeat size)r#z -maxrepeat maxrepeatzMaximum repeat sizez -thresholdrHzThreshold scorez -mismatchrtzAllow N as a mismatchz-uniformZuniformzAllow uniform consensusz-rformatrnzOutput report formatN)rrrr)rrrrrrrs   zETandemCommandline.__init__N)ry)rrrrrrrrrrxsrxc@seZdZdZdddZdS)EInvertedCommandlinez9Commandline object for the einverted program from EMBOSS. einvertedc Ksztddgddddtddgddddtd d gd dd td dgddd tddgddd tddgdg|_tj||f|dS)zInitialize the class.z -sequencer"rzT)rr#z-gapZgapz Gap penaltyz -thresholdrHzMinimum score threshold)r#z-matchrsz Match scorez -mismatchrtzMismatch scorez -maxrepeatr{z6Maximum separation between the start and end of repeatN)rrrr)rrrrrrrs zEInvertedCommandline.__init__N)r})rrrrrrrrrr|sr|c@seZdZdZdddZdS)PalindromeCommandlinez:Commandline object for the palindrome program from EMBOSS. palindromec Ks|tddgddddtddgddd td d gd dd td dgddd tddgddd tddgddd g|_tj||f|dS)zInitialize the class.z -sequencer"rzT)rr#z -minpallenZ minpallenzMinimum palindrome length)r#z -maxpallenZ maxpallenzMaximum palindrome lengthz -gaplimitZgaplimitzMaximum gap between repeatsz-nummismatchesZ nummismatcheszNumber of mismatches allowedz-overlapZoverlapzReport overlapping matchesN)rrrr)rrrrrrrs*zPalindromeCommandline.__init__N)r)rrrrrrrrrr~sr~c@seZdZdZdddZdS)TranalignCommandlinez9Commandline object for the tranalign program from EMBOSS. tranaligncKs\tddgddddtddgddddtd d gd dddtd d gdg|_tj||f|dS)zInitialize the class.z -asequencerSz#Nucleotide sequences to be aligned.T)rr#z -bsequencerTzProtein sequence alignmentz-outseqoutseqzOutput sequence file.z-tabletablez Code to useN)rrrr)rrrrrrrs"zTranalignCommandline.__init__N)r)rrrrrrrrrrsrc@seZdZdZdddZdS)DiffseqCommandlinez7Commandline object for the diffseq program from EMBOSS.diffseqc Ks~tddgddddtddgddddtd d gd dd td dgddddtddgddddtddgdg|_tj||f|dS)zInitialize the class.z -asequencerSzFirst sequence to compareT)rr#z -bsequencerTzSecond sequence to comparez -wordsizewordsizez-Word size to use for comparisons (10 default))r#z -aoutfeatZaoutfeatz,File for output of first sequence's featuresz -boutfeatZboutfeatz-File for output of second sequence's featuresz-rformatrnzOutput report file formatN)rrrr)rrrrrrrs4zDiffseqCommandline.__init__N)r)rrrrrrrrrr src@seZdZdZdddZdS)IepCommandlineaCommandline for EMBOSS iep: calculated isoelectric point and charge. Examples -------- >>> from Bio.Emboss.Applications import IepCommandline >>> iep_cline = IepCommandline(sequence="proteins.faa", ... outfile="proteins.txt") >>> print(iep_cline) iep -outfile=proteins.txt -sequence=proteins.faa You would typically run the command line with iep_cline() or via the Python subprocess module, as described in the Biopython tutorial. iepcKshtddgddddtddgdtd d gd td d gdtddgdtddgdg|_tj||f|dS)zInitialize the class.z -sequencer"zProtein sequence(s) filenameT)rr#z-aminoZaminozZNumber of N-termini Integer 0 (default) or more. z -carboxylZcarboxylzZNumber of C-termini Integer 0 (default) or more. z-lysinemodifiedZlysinemodifiedzaNumber of modified lysines Integer 0 (default) or more. z -disulphidesZ disulphideszcNumber of disulphide bridges Integer 0 (default) or more. z -noterminiZ noterminiz=Exclude (True) or include (False) charge at N and C terminus.N)rrrr)rrrrrrrCs* zIepCommandline.__init__N)r)rrrrrrrrrr3src@s"eZdZdZdddZddZdS) SeqretCommandlineaCommandline object for the seqret program from EMBOSS. This tool allows you to interconvert between different sequence file formats (e.g. GenBank to FASTA). Combining Biopython's Bio.SeqIO module with seqret using a suitable intermediate file format can allow you to read/write to an even wider range of file formats. This wrapper currently only supports the core functionality, things like feature tables (in EMBOSS 6.1.0 onwards) are not yet included. seqretcKsRtddgdddtddgdddtd d gd td d gdg|_tj||f|dS)zInitialize the class.z -sequencer"zInput sequence(s) filenameT)rz-outseqrzOutput sequence file.z-sformatZsformatz.Input sequence(s) format (e.g. fasta, genbank)z -osformatZosformatz/Output sequence(s) format (e.g. fasta, genbank)N)rrrr)rrrrrrr~s zSeqretCommandline.__init__cCs>|js|js|jstd|js4|js4|js4tdt|S)Nz]You must either set outfile (output filename), or enable filter or stdout (output to stdout).z\You must either set sequence (input filename), or enable filter or stdin (input from stdin).)rrrrr"Zstdintrr)rrrrrszSeqretCommandline._validateN)r)rrrrrrrrrrrrs  rc@seZdZdZdddZdS)SeqmatchallCommandlineakCommandline object for the seqmatchall program from EMBOSS. e.g. >>> cline = SeqmatchallCommandline(sequence="opuntia.fasta", outfile="opuntia.txt") >>> cline.auto = True >>> cline.wordsize = 18 >>> cline.aformat = "pair" >>> print(cline) seqmatchall -auto -outfile=opuntia.txt -sequence=opuntia.fasta -wordsize=18 -aformat=pair seqmatchallcKsDtddgddddtddgdtd d gd g|_tj||f|d S) zInitialize the class.z -sequencer"zReadable set of sequencesT)rr#z -wordsizerz(Word size (Integer 2 or more, default 4)z-aformatrZz5Display output in a different specified output formatN)rrrr)rrrrrrrs  zSeqmatchallCommandline.__init__N)r)rrrrrrrrrrs r__main__) run_doctestN)#rZBio.Applicationrrrrrr r&r+r6r:r@rDrIrLrNrQr[r`rcrjrorqrxr|r~rrrrrrZ Bio._utilsrrrrrs@@$:$& &****49+1$(?/!